Skip to main content
POST
/
generate-video
/
extend
cURL
curl --request POST \
  --url https://nano-gpt.com/api/generate-video/extend \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "taskId": "vid_m1abc123def456",
  "index": 0
}
'
{
  "runId": "<string>",
  "status": "pending",
  "model": "<string>",
  "projectId": "<string>",
  "cost": 123,
  "paymentSource": "<string>",
  "remainingBalance": 123,
  "prechargeLabel": "<string>"
}

​
Overview

This endpoint is the task-based extension flow for Midjourney videos. For all other extend models, use POST /api/generate-video with a source video.

​
Endpoint

POST /api/generate-video/extend

​
Rate limit

20 requests/minute per IP

​
Supported models (task-based)

  • midjourney-video (extend a Midjourney video created via POST /api/generate-video)

​
Required fields (Midjourney extend)

  • runId (preferred) or taskId (legacy alias): the job ID from the original Midjourney video request
  • index (0-3)
index maps to the 4 videos returned by the original Midjourney request.

​
Request notes

  • Send the same authentication headers as /api/generate-video.
  • Session ownership is enforced; requests for jobs you do not own return 403.
  • This endpoint does not accept video, videoUrl, videoDataUrl, or videoAttachmentId.
  • The response format matches the standard generation response (runId, id, status, model, cost).

​
Source video extend (use /api/generate-video)

Use POST /api/generate-video with an extend model and a source video input. Extend model examples:
  • wan-wavespeed-22-spicy-extend
  • wan-wavespeed-25-extend
  • veo3-1-extend
  • veo3-1-fast-extend
  • bytedance-seedance-v1.5-pro-extend
Required fields:
  • prompt
  • videoUrl (or videoDataUrl / videoAttachmentId)
Notes:
  • video is only accepted by specific models (for example, wan-wavespeed-25-extend).
  • wan-wavespeed-22-spicy-extend accepts videoUrl, videoDataUrl, or videoAttachmentId only.
  • Max source video length: 120 seconds.

​
Example: Midjourney extend (task-based)

{
  "runId": "vid_m1abc123def456",
  "index": 0
}

​
Example response

{
  "success": true,
  "runId": "vid_m1abc123def456",
  "id": "vid_m1abc123def456",
  "taskId": "vid_m1abc123def456",
  "status": "pending",
  "model": "midjourney-video",
  "message": "Extending video 1 by 5 seconds...",
  "eta": 60
}

​
Example: Source video extend (/api/generate-video)

{
  "model": "wan-wavespeed-22-spicy-extend",
  "prompt": "Extend the clip with smooth motion and warm light",
  "videoUrl": "https://example.com/source.mp4",
  "resolution": "480p",
  "duration": 5,
  "seed": -1
}

Authorizations

​
x-api-key
string
header
required

Body

application/json

Midjourney extension request payload (taskId from the original run + index).

​
taskId
string
required

Run ID from the original Midjourney video request.

​
index
integer
required

Zero-based index of the Midjourney video to extend (0-3).

Required range: 0 <= x <= 3

Response

Video extension request submitted successfully (asynchronous processing)

​
runId
string
required

Unique identifier for the video generation request

​
status
enum<string>
default:pending
required

Current status of the generation

Available options:
pending,
processing,
completed,
failed
​
model
string
required

The model used for generation

​
projectId
string

Project identifier (for LongStories models)

​
cost
number

Cost of the video generation

​
paymentSource
string

Payment source used (USD or XNO)

​
remainingBalance
number

Remaining balance after the generation

​
prechargeLabel
string

Provider label for the precharge